Polyseme discovery method and device
A method for discovering polysemous words, which is applied in the field of polysemous words discovery, can solve the problems of consuming computing resources, long time-consuming, and high complexity, and achieve the effects of improving computing efficiency, speeding up acquisition speed, and accurate semantic expression
Inactive Publication Date: 2019-05-14
SHANGHAI XIAOI ROBOT TECH CO LTD
View PDF5 Cites 7 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the calculation of word vectors mostly uses large-scale neural networks, especially to obtain polysemy word vectors from multi-layer context-dependent language models, which requires a huge amount of calculation and takes a long time.
In addition, these applications are usually used in downstream natural language processing tasks, such as reading comprehension, sequence labeling, question answering systems, etc., making the entire task more complex and greatly consuming computing resources
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0071] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
[0072] In one embodiment of the present invention, as figure 1 As shown, a polysemous word discovery method is provided, including the following steps:
[0073] Step S100: Acquire natural language corpus;
[0074] Step S200: Segment the natural language corpus into a plurality of first sentence subsets;
[0075] Step S300: Find polysemy words in each of the first sentence subsets, and all the polysemous words in each of the first sentence subse...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention provides a polysemy discovering method. The polysemy discovering method comprises: obtaining natural language corpora; segmenting the natural language corpus into a plurality of first sentence subsets; searching polysemes in each first sentence subset, wherein all polysemes in each first sentence subset form a polyseme set of the first sentence subset; and combining the polyseme setsof all the first sentence subsets to form a polyseme dictionary. The generated polysemy dictionary can be used for searching polysemy words, polysemy word vectors can be obtained through fast indexing in an application, through the above steps, the step of obtaining the polysemy word vectors can be simplified, and on the basis that the expression accuracy of the word vectors is guaranteed, the overall calculation efficiency of natural language processing tasks is improved.
Description
technical field [0001] The invention relates to the technical field of computer natural language processing, in particular to a method and device for discovering polysemous words. Background technique [0002] In the field of natural language processing, the disambiguation of polysemous words has always been a hot research issue in this field. At present, a language model with contextual characteristics is usually used, and polysemous words are discriminated through calculated word vectors, which are applied in downstream specific natural language processing tasks. However, the calculation of word vectors mostly uses large-scale neural networks, especially to obtain polysemy word vectors from multi-layer context-dependent language models, which requires a huge amount of calculation and takes a long time. In addition, these applications are usually used in downstream natural language processing tasks, such as reading comprehension, sequence labeling, question answering syste...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/36G06F17/27
Inventor 沈大框陈培华陈成才
Owner SHANGHAI XIAOI ROBOT TECH CO LTD